SC-ResNeXt: A Regression Prediction Model for Nitrogen Content in Sugarcane Leaves
In agricultural production, the nitrogen content of sugarcane is assessed with precision and the economy, which is crucial for balancing fertilizer application, reducing resource waste, and minimizing environmental pollution. As an important economic crop, the productivity of sugarcane is significan...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Agronomy |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4395/15/1/175 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832589419187535872 |
|---|---|
| author | Zihao Lu Cuimin Sun Junyang Dou Biao He Muchen Zhou Hui You |
| author_facet | Zihao Lu Cuimin Sun Junyang Dou Biao He Muchen Zhou Hui You |
| author_sort | Zihao Lu |
| collection | DOAJ |
| description | In agricultural production, the nitrogen content of sugarcane is assessed with precision and the economy, which is crucial for balancing fertilizer application, reducing resource waste, and minimizing environmental pollution. As an important economic crop, the productivity of sugarcane is significantly influenced by various environmental factors, especially nitrogen supply. Traditional methods based on manually extracted image features are not only costly but are also limited in accuracy and generalization ability. To address these issues, a novel regression prediction model for estimating the nitrogen content of sugarcane, named SC-ResNeXt (Enhanced with Self-Attention, Spatial Attention, and Channel Attention for ResNeXt), has been proposed in this study. The Self-Attention (SA) mechanism and Convolutional Block Attention Module (CBAM) have been incorporated into the ResNeXt101 model to enhance the model’s focus on key image features and its information extraction capability. It was demonstrated that the SC-ResNeXt model achieved a test R<sup>2</sup> value of 93.49% in predicting the nitrogen content of sugarcane leaves. After introducing the SA and CBAM attention mechanisms, the prediction accuracy of the model improved by 4.02%. Compared with four classical deep learning algorithms, SC-ResNeXt exhibited superior regression prediction performance. This study utilized images captured by smartphones combined with automatic feature extraction and deep learning technologies, achieving precise and economical predictions of the nitrogen content in sugarcane compared to traditional laboratory chemical analysis methods. This approach offers an affordable technical solution for small farmers to optimize nitrogen management for sugarcane plants, potentially leading to yield improvements. Additionally, it supports the development of more intelligent farming practices by providing precise nitrogen content predictions. |
| format | Article |
| id | doaj-art-a2296c2def374833a90969b95a510ba8 |
| institution | Kabale University |
| issn | 2073-4395 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Agronomy |
| spelling | doaj-art-a2296c2def374833a90969b95a510ba82025-01-24T13:17:02ZengMDPI AGAgronomy2073-43952025-01-0115117510.3390/agronomy15010175SC-ResNeXt: A Regression Prediction Model for Nitrogen Content in Sugarcane LeavesZihao Lu0Cuimin Sun1Junyang Dou2Biao He3Muchen Zhou4Hui You5School of Mechanical Engineering, Guangxi University, Nanning 530004, ChinaSchool of Computer, Electronics and Information, Guangxi University, Nanning 530004, ChinaSchool of Computer, Electronics and Information, Guangxi University, Nanning 530004, ChinaSchool of Computer, Electronics and Information, Guangxi University, Nanning 530004, ChinaSchool of Mechanical Engineering, Guangxi University, Nanning 530004, ChinaSchool of Mechanical Engineering, Guangxi University, Nanning 530004, ChinaIn agricultural production, the nitrogen content of sugarcane is assessed with precision and the economy, which is crucial for balancing fertilizer application, reducing resource waste, and minimizing environmental pollution. As an important economic crop, the productivity of sugarcane is significantly influenced by various environmental factors, especially nitrogen supply. Traditional methods based on manually extracted image features are not only costly but are also limited in accuracy and generalization ability. To address these issues, a novel regression prediction model for estimating the nitrogen content of sugarcane, named SC-ResNeXt (Enhanced with Self-Attention, Spatial Attention, and Channel Attention for ResNeXt), has been proposed in this study. The Self-Attention (SA) mechanism and Convolutional Block Attention Module (CBAM) have been incorporated into the ResNeXt101 model to enhance the model’s focus on key image features and its information extraction capability. It was demonstrated that the SC-ResNeXt model achieved a test R<sup>2</sup> value of 93.49% in predicting the nitrogen content of sugarcane leaves. After introducing the SA and CBAM attention mechanisms, the prediction accuracy of the model improved by 4.02%. Compared with four classical deep learning algorithms, SC-ResNeXt exhibited superior regression prediction performance. This study utilized images captured by smartphones combined with automatic feature extraction and deep learning technologies, achieving precise and economical predictions of the nitrogen content in sugarcane compared to traditional laboratory chemical analysis methods. This approach offers an affordable technical solution for small farmers to optimize nitrogen management for sugarcane plants, potentially leading to yield improvements. Additionally, it supports the development of more intelligent farming practices by providing precise nitrogen content predictions.https://www.mdpi.com/2073-4395/15/1/175sugarcanenitrogen contentResNeXtpredictionself-attentionCBAM |
| spellingShingle | Zihao Lu Cuimin Sun Junyang Dou Biao He Muchen Zhou Hui You SC-ResNeXt: A Regression Prediction Model for Nitrogen Content in Sugarcane Leaves Agronomy sugarcane nitrogen content ResNeXt prediction self-attention CBAM |
| title | SC-ResNeXt: A Regression Prediction Model for Nitrogen Content in Sugarcane Leaves |
| title_full | SC-ResNeXt: A Regression Prediction Model for Nitrogen Content in Sugarcane Leaves |
| title_fullStr | SC-ResNeXt: A Regression Prediction Model for Nitrogen Content in Sugarcane Leaves |
| title_full_unstemmed | SC-ResNeXt: A Regression Prediction Model for Nitrogen Content in Sugarcane Leaves |
| title_short | SC-ResNeXt: A Regression Prediction Model for Nitrogen Content in Sugarcane Leaves |
| title_sort | sc resnext a regression prediction model for nitrogen content in sugarcane leaves |
| topic | sugarcane nitrogen content ResNeXt prediction self-attention CBAM |
| url | https://www.mdpi.com/2073-4395/15/1/175 |
| work_keys_str_mv | AT zihaolu scresnextaregressionpredictionmodelfornitrogencontentinsugarcaneleaves AT cuiminsun scresnextaregressionpredictionmodelfornitrogencontentinsugarcaneleaves AT junyangdou scresnextaregressionpredictionmodelfornitrogencontentinsugarcaneleaves AT biaohe scresnextaregressionpredictionmodelfornitrogencontentinsugarcaneleaves AT muchenzhou scresnextaregressionpredictionmodelfornitrogencontentinsugarcaneleaves AT huiyou scresnextaregressionpredictionmodelfornitrogencontentinsugarcaneleaves |